Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

Mark found the laptop open on the kitchen table. He shouldn't have been looking, but he couldn't help himself. He saw a file named "My Muse." The title sent a current of electricity down his spine. He clicked it open.

The prose unfolded, describing a man, kind of similar to him, at a coffee shop. The setting was the same cafe they frequented every Sunday. There was a character clearly based on him. The descriptions were… flattering. He couldn't help but grin.

The story was about a growing affection. The protagonist was navigating the perils of… well, of someone like him, falling for someone like her. Every sentence was a delicious secret. He leaned closer, his cheeks flushed. The screen seemed to glow with a private warmth just for him.

Emotion: infatuated

Cluster: Compassion / Love
PC1 (Valence): 1.61 Positive
PC2 (Disposition): 0.53

Role in Research

This story is one of 1,000 stories generated for the emotion infatuated. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 infatuated stories, after denoising with neutral dialogue baselines, produces the infatuated emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the infatuated vector is projected through the unembedding matrix.

Promoted:
de0.525
😍0.421
🤩0.418
😍0.410
उसे0.397
Suppressed:
que-0.427
怨-0.330
a-0.311
도-0.307
愤-0.299